© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 3156
    Prev
    Next
    INDEX
    Explanations

    superscripted single quotes following the letter I or the underscore character, and the equals sign in HTML

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bil
    -0.68
     žem
    -0.60
    antMatchers
    -0.60
    {~
    -0.59
     __
    -0.58
    Gön
    -0.58
     Jordi
    -0.56
     AssemblyVersion
    -0.56
     sacks
    -0.56
    ikan
    -0.55
    POSITIVE LOGITS
    '_
    2.00
    ="_
    1.92
     '_
    1.75
     "_
    1.58
    "_
    1.53
    ='_
    1.53
    ('_
    1.38
    ("_
    1.34
    ['_
    1.30
    ["_
    1.14
    Activations Density 0.012%

    No Known Activations